Explore data

Get data

Last execution time: 07/04/2025 05:42:46

explore_types = ['frutas', 'lacteos', 'verduras', 'embutidos', 'panaderia', 'desayuno', 'congelados', 'abarrotes',
                 'aves', 'carnes', 'pescados']

path = Path('../../output')
csv_files = L(path.glob('*.csv')).filter(lambda o: os.stat(o).st_size>0)
pat_store = re.compile('(.+)\_\d+')
pat_date = re.compile('.+\_(\d+)')
df = (
    pd.concat([pd.read_csv(o).assign(store=pat_store.match(o.stem)[1], date=pat_date.match(o.stem)[1])
               for o in csv_files], ignore_index=True)
    .pipe(lambda d: d.assign(
        name=d.name.str.lower()+' ('+d.store+')',
        sku=d.id.where(d.sku.isna(), d.sku).astype(int),
        date=pd.to_datetime(d.date)
    ))
    .drop('id', axis=1)
    .loc[lambda d: d.category.str.contains('|'.join(explore_types))]
    # Filter products with recent data
#     .loc[lambda d: d.name.isin(d.groupby('name').date.max().loc[ge(datetime.now()-timedelta(days=30))].index)]
    # Filter empty prices
    .loc[lambda d: d.price>0]
)
print(df.shape)
df.sample(3)

(1331183, 8)

	sku	name	brand	category	uri	price	store	date
792638	11069381	pasta de ajo walibi doypack 85g (plaza_vea)	WALIBI	https://www.plazavea.com.pe/abarrotes	https://www.plazavea.com.pe/pasta-de-ajo-walib...	3.29	plaza_vea	2024-01-15
1175665	10588582	chuletón de pierna redondos duroc x kg (plaza_...	REDONDOS	https://www.plazavea.com.pe/carnes-aves-y-pesc...	https://www.plazavea.com.pe/chuleton-de-pierna...	30.90	plaza_vea	2024-08-26
1853605	10215193	galletas rellenitas de fresa paquete 90g (plaz...	GN	https://www.plazavea.com.pe/abarrotes	https://www.plazavea.com.pe/galletas-rellenita...	2.50	plaza_vea	2025-03-24

Top changes (ratio)

top_changes = (df
 # Use last 30 days of data to compare prices
 .loc[lambda d: d.date>=(datetime.now()-timedelta(days=30))]
 .sort_values('date')
 # Get percentage change
 .assign(change=lambda d: d
     .groupby(['store','sku'], as_index=False)
     .price.transform(lambda d: (d-d.shift())/d.shift())
 )
 .groupby(['store','sku'], as_index=False)
 .agg({'price':'last', 'change':'mean', 'date':'last'})
 .rename({'price':'last_price', 'date':'last_date'}, axis=1)
 .dropna()
 .loc[lambda d: d.last_date==d.last_date.max()]
 .loc[lambda d: d.change.abs().sort_values(ascending=False).index]
)
top_changes.head(3)

	store	sku	last_price	change	last_date
536	plaza_vea	2574	7.9	0.919435	2025-04-07
591	plaza_vea	2919	4.2	-0.330215	2025-04-07
643	plaza_vea	3083	6.2	-0.247276	2025-04-07

def plot_changes(df_changes, title):
    selection = alt.selection_point(fields=['name'], bind='legend')
    dff = df_changes.drop('change', axis=1).merge(df, on=['store','sku'])
    return (dff
     .pipe(alt.Chart)
     .mark_line(point=True)
     .encode(
         x='date',
         y='price',
         color=alt.Color('name').scale(domain=sorted(dff.name.unique().tolist())),
         tooltip=['name','price','last_price']
     )
     .add_params(selection)
     .transform_filter(selection)
     .interactive()
     .properties(width=650, title=title)
     .configure_legend(orient='top', columns=3)
    )

top_changes.head(10).pipe(plot_changes, 'Top changes')

(top_changes
 .sort_values('change')
 .head(10)
 .pipe(plot_changes, 'Top drops')
)

(top_changes
 .sort_values('change')
 .tail(10)
 .pipe(plot_changes, 'Top increases')
)

Top changes (absolute values)

top_changes_abs = (df
 # Use last 30 days of data to compare prices
 .loc[lambda d: d.date>=(datetime.now()-timedelta(days=30))]
 .sort_values('date')
 # Get percentage change
 .assign(change=lambda d: d
     .groupby(['store','sku'], as_index=False)
     .price.transform(lambda d: (d-d.shift()).iloc[-1])
 )
 .groupby(['store','sku'], as_index=False)
 .agg({'price':'last', 'change':'mean', 'date':'last'})
 .rename({'price':'last_price', 'date':'last_date'}, axis=1)
 .dropna()
 .loc[lambda d: d.last_date==d.last_date.max()]
 .loc[lambda d: d.change.abs().sort_values(ascending=False).index]
)
top_changes_abs.head(3)

	store	sku	last_price	change	last_date
2576	plaza_vea	10037893	251.0	45.4	2025-04-07
2350	plaza_vea	10012680	157.5	44.7	2025-04-07
5766	plaza_vea	11737880	99.9	21.9	2025-04-07

top_changes_abs.head(10).pipe(plot_changes, 'Top changes')

(top_changes_abs
 .sort_values('change')
 .head(10)
 .pipe(plot_changes, 'Top drops')
)

(top_changes_abs
 .sort_values('change')
 .tail(10)
 .pipe(plot_changes, 'Top increases')
)

Search specific products

(df
 .loc[df.name.isin(names)]
 .pipe(alt.Chart)
 .mark_line(point=True)
 .encode(x='date', y='price', color='name', tooltip=['name','price'])
 .properties(width=650, title='Pollo')
 .interactive()
 .configure_legend(orient='top', columns=3)
)

(df
 .loc[df.name.isin(names)]
 .pipe(alt.Chart)
 .mark_line(point=True)
 .encode(x='date', y='price', color='name', tooltip=['name','price'])
 .properties(width=650, title='Palta')
 .interactive()
 .configure_legend(orient='top', columns=3)
)

(df
 .loc[df.name.isin(names)]
 .pipe(alt.Chart)
 .mark_line(point=True)
 .encode(x='date', y='price', color='name', tooltip=['name','price'])
 .properties(width=650, title='Aceite')
 .interactive()
 .configure_legend(orient='top', columns=3)
)

(df
 .loc[df.name.isin(names)]
 .pipe(alt.Chart)
 .mark_line(point=True)
 .encode(x='date', y='price', color='name', tooltip=['name','price'])
 .properties(width=650, title='Aceite')
 .interactive()
 .configure_legend(orient='top', columns=3)
)

(df
 .loc[df.name.isin(names)]
 .pipe(alt.Chart)
 .mark_line(point=True)
 .encode(x='date', y='price', color='name', tooltip=['name','price'])
 .properties(width=650, title='Aceite')
 .interactive()
 .configure_legend(orient='top', columns=3)
)